← all publishers

agentskillexchange

@agentskillexchange source repo

Report this profile Claim this profile

• 2.9k skills
• 0 followers
• 28 repo stars
• 2 weeks ago last updated

1. ▌
   Track Coding Agent Quota Burn And Remaining Headroom Across · agentskillexchange

   Monitor quota, spend, resets, and alerts across multiple coding-agent providers from one local dashboard before a long run hits throttling or budget limits.
   28 repo stars
2. ▌
   Capture Youtube Transcripts Without Browser Automation Using · agentskillexchange

   Fetch manual or auto-generated YouTube subtitles, including translations, without Selenium or API keys before summarization, extraction, or quote-checking.
   28 repo stars
3. ▌
   Detect Scene Boundaries And Export Cut Lists Before Video Re · agentskillexchange

   Detect scene changes in a video, emit cut boundaries, and hand back machine-usable scene lists before manual review, splitting, or clip assembly.
   28 repo stars
4. ▌
   Draft User Facing App Store Release Notes From Git History W · agentskillexchange

   Turn commits since the last tag into concise App Store What's New bullets instead of hand-sifting raw git history.
   28 repo stars
5. ▌
   Embed Bounded Claude Code Sessions Into Python Automation Wi · agentskillexchange

   Use the Claude Agent SDK for Python when an existing script or service needs to delegate scoped repo work to Claude Code and consume structured responses programmatically.
   28 repo stars
6. ▌
   Format Citations And Bibliographies From Dois Urls Bibtex An · agentskillexchange

   Use Citation.js when an agent has raw references and needs clean citation output instead of hand-formatting sources. It can resolve supported identifiers, normalize metadata into CSL-JSON, and emit bibliography or inline citation formats that fit articles, research notes, docs, or release materials.
   28 repo stars
7. ▌
   Generate And Validate Conventional Commits And Semver Releas · agentskillexchange

   Standardize commit messages, validate commit history, and calculate semver-aware release bumps without hand-rolled repo rules.
   28 repo stars
8. ▌
   Investigate Production Incidents Across Kubernetes And Cloud · agentskillexchange

   Use HolmesGPT when an on-call agent needs one investigation loop that pulls alerts, logs, metrics, and infrastructure context from multiple systems and returns a root-cause path instead of forcing a human to hop across separate observability products.
   28 repo stars
9. ▌
   Lint Ansible Playbooks And Roles Before Automation Breaks In · agentskillexchange

   Run ansible-lint against playbooks, roles, and collections so risky patterns and common mistakes are caught before automation is merged or executed.
   28 repo stars
10. ▌
    Prove Whether A Prompt Or Model Variant Really Won Before Sh · agentskillexchange

    Run statistically sound comparisons on eval results so prompt and model changes are judged by confidence bounds, not bar-chart vibes.
    28 repo stars
11. ▌
    Scan Agent Workflows For Tools MCP Exposure And Adversarial · agentskillexchange

    Use Agentic Radar to statically scan agent workflows, map tools and MCP servers, generate shareable security reports, and optionally run adversarial runtime tests before rollout.
    28 repo stars
12. ▌
    Scan Repositories For AI Supply Chain And Agent Security Ris · agentskillexchange

    Use Medusa Security before trusting a repository, dependency, or AI-agent codebase when an agent needs a focused scan for repo poisoning, prompt-injection, MCP, and AI supply-chain findings.
    28 repo stars
13. ▌
    Store Selective Long Term Agent Memories With Mem0 Instead O · agentskillexchange

    Use Mem0 when an agent should retain durable preferences, facts, and prior decisions as selective memory records instead of stuffing more transcript history back into every prompt.
    28 repo stars
14. ▌
    Turn Captured Warc Pages Into Clean Text And Language Tagged · agentskillexchange

    Use warc2text when an agent already has WARC captures and needs readable text, language identification, and exportable records for review, search, or corpus building instead of re-crawling pages.
    28 repo stars
15. ▌
    Turn Markdown Or Raw Content Into Agent Generated HTML Artif · agentskillexchange

    Run a local agentic HTML editor that detects coding-agent CLIs, streams generated HTML into a sandboxed preview, and exports pages, decks, posters, reports, and social assets.
    28 repo stars
16. ▌
    Wrap Local Coding Agents In Deny By Default Least Privilege · agentskillexchange

    Run Claude Code, Codex, Cursor, or similar local agent CLIs inside a host-local sandbox that learns required access and blocks everything else by default.
    28 repo stars
17. ▌
    Analyze Memory Images For Processes Modules And Malware Indi · agentskillexchange

    Inspect captured RAM images to enumerate processes, modules, handles, and suspicious in-memory behavior before escalation or evidence handoff.
    28 repo stars
18. ▌
    Automate Notebooklm Studio Generation And Cited Research Bat · agentskillexchange

    Use NotebookLM through MCP or a local REST API to run cited Q&A, generate Studio artifacts, and manage high-volume research batches.
    28 repo stars
19. ▌
    Diff YAML Manifests Semantically And Surface Meaningful Drif · agentskillexchange

    Use dyff to compare YAML documents by structure and changed paths so agents can review configuration drift without the noise of plain line diffs.
    28 repo stars
20. ▌
    Ingest Chinese Social And Media Content Into Agent Knowledge · agentskillexchange

    Use Chubbyskills when an agent needs installable skills for collecting Chinese social, video, podcast, and article content into Markdown and Obsidian-style knowledge bases.
    28 repo stars
21. ▌
    Manage Multi Agent Coding Sessions From One Terminal Mission · agentskillexchange

    Use Agent Deck when an operator needs one keyboard-first terminal to monitor, switch, fork, sandbox, and organize many coding-agent sessions instead of juggling tabs, panes, and worktrees by hand.
    28 repo stars
22. ▌
    Mirror Openclaw Workspaces And Stream Encrypted Backups With · agentskillexchange

    Sync an OpenClaw workspace to your own cloud storage or push encrypted agent-system backups with OpenClaw-aware mailbox, mirror, and bisync modes.
    28 repo stars
23. ▌
    Normalize Dbt SQL And Jinja Templates Into Consistent Review · agentskillexchange

    Use sqlfmt to reformat dbt-oriented SQL and Jinja-heavy query files into a stable style before code review, CI checks, or agent-generated handoff.
    28 repo stars
24. ▌
    Provision Secure Disposable Development Sandboxes For AI Gen · agentskillexchange

    Spin up isolated, reproducible sandboxes where agents can run generated code, install dependencies, execute tests, and discard state safely.
    28 repo stars
25. ▌
    Scaffold And Bundle Rich Single File Web Artifacts With Reac · agentskillexchange

    Use Anthropic's web-artifacts-builder skill to scaffold a React artifact project, build a richer interface with state or routing, and bundle everything into one shareable HTML file. It is for artifact-delivery workflows, not for listing React or Tailwind as standalone products.
    28 repo stars
26. ▌
    Trace Unstable Network Paths And Packet Loss With Trippy Bef · agentskillexchange

    Measure route hops, latency, jitter, and packet loss to isolate where a network path degrades during incidents.
    28 repo stars
27. ▌
    Turn Feature Ideas Into Executable Implementation Specs And · agentskillexchange

    Use Spec Kit when an agent should turn a feature idea into a spec-first workflow with explicit artifacts, planning steps, and task breakdowns before code is written.
    28 repo stars
28. ▌
    Benchmark Browser Agents On A Fixed Stealth And Task Suite W · agentskillexchange

    Compare browser-agent reliability on a repeatable task and anti-bot suite before choosing a stack or claiming progress.
    28 repo stars
29. ▌
    Catch Agent Era CI CD And Permission Misconfigurations Befor · agentskillexchange

    Run Ship Safe before a release when an agent needs one pre-ship pass for CI/CD misconfigurations, permission risks, secrets exposure, MCP-related hazards, and dependency issues.
    28 repo stars
30. ▌
    Compare Recurring CSV Tsv Or JSON Exports And Emit Row Level · agentskillexchange

    Use csv-diff when an agent needs to explain what changed between two structured exports, not just that the files differ. The agent lines records up by a stable key, reports added, removed, and changed rows, and can hand the result to humans or downstream automations as readable text or machine-friendly JSON.
    28 repo stars
31. ▌
    Generate LLM Fine Tuning RAG And Eval Datasets From Source M · agentskillexchange

    Turn raw documents into structured fine-tuning, RAG, and evaluation datasets when the real job is dataset preparation, not generic document parsing.
    28 repo stars
32. ▌
    Layer Self Correcting Memory And Worktree Routines Into Clau · agentskillexchange

    Use Pro Workflow when Claude Code sessions keep repeating the same mistakes and you want corrections, quality gates, and parallel worktree routines to persist across sessions instead of being re-explained every time.
    28 repo stars
33. ▌
    Probe Kubernetes Clusters With Kube Hunter For Exposed Servi · agentskillexchange

    Run a focused exposure probe against a Kubernetes environment before deeper pentest work or remediation planning starts.
    28 repo stars
34. ▌
    Run Repeatable Model And Agent Eval Suites And Inspect Scori · agentskillexchange

    Run benchmark-style eval suites against models or agents, then inspect scored traces instead of relying on ad hoc chats and gut feel.
    28 repo stars
35. ▌
    Scan Repositories For Shai Hulud 2 0 Supply Chain Indicators · agentskillexchange

    Check repositories and CI surfaces for Shai-Hulud 2.0 compromise indicators when the task is targeted supply-chain triage, not generic malware scanning.
    28 repo stars
36. ▌
    Simulate Buyer And User Personas To Pressure Test Ideas And · agentskillexchange

    Use TinyTroupe when an agent should run simulated persona panels, synthetic interviews, or offline audience reactions before spending on campaigns, launches, or user research.
    28 repo stars
37. ▌
    Summarize Failing Go Test Runs And Rerun Flakes Before CI Re · agentskillexchange

    Use gotestsum to turn noisy `go test` output into compact failure summaries, JUnit or JSON artifacts, and optional reruns of flaky tests before an agent starts fixing Go code.
    28 repo stars
38. ▌
    Tune Supabase Postgres Queries Indexing And Rls With Supabas · agentskillexchange

    Review Supabase Postgres work for query performance, schema design, indexing, connection handling, and RLS pitfalls using Supabase's own prioritized guidance.
    28 repo stars
39. ▌
    Turn Ics Calendar Invites And Feeds Into Structured Events F · agentskillexchange

    Use node-ical when an agent is handed a raw .ics file or subscription URL and needs normalized event objects, recurrence-aware dates, and timezone-safe fields it can reason over. The skill stops at parsing and structuring calendar data, not acting as a full calendar product.
    28 repo stars
40. ▌
    Benchmark It Automation Agents On Realistic Sre Ciso And Fin · agentskillexchange

    Run realistic enterprise-style IT scenarios before trusting an automation agent in production operations.
    28 repo stars
41. ▌
    Benchmark Virtual Agents With Scripted Multi Turn Conversati · agentskillexchange

    Run concurrent scripted conversations against a target agent to measure whether it stays on task, responds correctly, and holds up in repeatable test cases.
    28 repo stars
42. ▌
    Catch Silent Agent Regressions By Diffing Outputs And Tool T · agentskillexchange

    Snapshot agent behavior, compare outputs and tool-call paths, and block releases when a model or prompt change quietly shifts behavior.
    28 repo stars
43. ▌
    Compose Typed Openclaw Workflows With Approval Gates And Res · agentskillexchange

    Use Lobster when an OpenClaw operator wants one deterministic typed workflow step, with approval gates and resumable execution, instead of re-planning the same multi-step tool sequence in chat.
    28 repo stars
44. ▌
    Fuzz Web Paths Parameters And Virtual Hosts With Ffuf To Sur · agentskillexchange

    Probe for hidden routes, parameter behaviors, and vhost exposures fast, before you spend time manually poking at the wrong surface.
    28 repo stars
45. ▌
    Normalize Article Metadata From Urls Before Generating Link · agentskillexchange

    Uses metascraper to turn a URL plus its fetched HTML into normalized fields such as title, description, author, date, publisher, and lead image. This is useful when an agent needs reliable preview or briefing data from a page without building a custom parser for every site.
    28 repo stars
46. ▌
    Regression Test LLM Apps And Agents With Metrics Traces And · agentskillexchange

    Run repeatable eval suites against prompts, RAG pipelines, and agents so regressions surface before release.
    28 repo stars
47. ▌
    Run Blocked Site Browser Tasks Through Anti Bot Friendly Ses · agentskillexchange

    Use Camofox Browser to route agent browser work through an anti-detection browser server with stable element refs, snapshots, cookies, proxies, and session isolation.
    28 repo stars
48. ▌
    Audit And Normalize Spdx License Headers Before Releasing Or · agentskillexchange

    Use REUSE when an agent needs file-level licensing clarity instead of guessing from a single top-level LICENSE file. The agent checks compliance, adds or verifies SPDX headers, pulls missing license texts into LICENSES/, and produces a concrete remediation list or SPDX export.
    28 repo stars
49. ▌
    Audit Ssh Servers And Clients For Weak Algorithms And Risky · agentskillexchange

    Inspect an SSH endpoint or config for outdated ciphers, key exchange choices, and hardening gaps before exposure or upgrades.
    28 repo stars
50. ▌
    Calculate Routes Etas And Place Lookups Inside Agent Plannin · agentskillexchange

    Gives an MCP-compatible agent structured place search, geocoding, routing, ETA, traffic, and map lookups so travel, field-service, and logistics tasks can stay inside an automated planning workflow.
    28 repo stars
51. ▌
    Capture And Replay Claude Code Trajectories For Multi Sessio · agentskillexchange

    Record structured Claude Code trajectories, shadow git diffs, and replay branches when agent behavior needs forensic debugging instead of ad hoc transcript review.
    28 repo stars
52. ▌
    Diagnose Pathological Git Repository Size Before Migration C · agentskillexchange

    Uses git-sizer to identify the specific size and history characteristics that make a repository painful to clone, fetch, repack, or work in. Use it when an agent needs evidence about large blobs, oversized trees, too many refs, or other Git pathologies before proposing cleanup.
    28 repo stars
53. ▌
    Generate And Iterate On A Local Codebase From A Natural Lang · agentskillexchange

    Use gpt-engineer when an agent/operator needs to turn a prompt file into a local project scaffold, inspect the generated code, and run a supervised improvement loop before adopting the result.
    28 repo stars
54. ▌
    Lint Live Kubernetes Clusters For Misconfigurations And Oper · agentskillexchange

    Inspect a live Kubernetes cluster for unhealthy resource settings, missing probes, and other operational smells.
    28 repo stars
55. ▌
    Mirror And Back Up Openclaw Workspaces To Your Own Storage W · agentskillexchange

    Lets an OpenClaw agent sync its workspace to cloud storage in mailbox, mirror, or bisync mode, and optionally push encrypted full-system backups to an rclone backend.
    28 repo stars
56. ▌
    Rewrite Git History To Purge Secrets Binaries Or Accidental · agentskillexchange

    Use git-filter-repo when an agent needs to surgically rewrite repository history after a leaked secret, a huge binary commit, or a bad subtree split. The agent analyzes the problem, builds the rewrite command, and leaves a clean follow-up checklist for force-push, clone reset, and downstream cleanup.
    28 repo stars
57. ▌
    Run Chinese First Academic Writing Office And Scientific Wor · agentskillexchange

    Install and invoke a Chinese-first academic skill bundle for paper writing, editable Word/PPT research documents, and scientific computing tasks in Claude Code or Codex.
    28 repo stars
58. ▌
    Run High Volume S3 Copy Sync And Delete Jobs Faster Than Ad · agentskillexchange

    Execute large parallel object-store operations from command files or shell pipelines when agents need speed and repeatability beyond basic aws s3 loops.
    28 repo stars
59. ▌
    Simulate Agent Scenarios Trace Failures And Watch Production · agentskillexchange

    Run end-to-end agent simulations, review traces, and watch production regressions when reliability work spans pre-release testing and live monitoring.
    28 repo stars
60. ▌
    Test Claude Code Plugin And Skill Triggering With Staged Eva · agentskillexchange

    Run staged evaluations against a Claude Code plugin to verify that skills, agents, commands, hooks, and MCP components trigger when they should.
    28 repo stars
61. ▌
    Test Documentation Sites Across Mobile Tablet And Desktop Wi · agentskillexchange

    Run a repeatable docs-site check that builds locally, opens the site across device sizes, and reports layout, accessibility, and interaction issues.
    28 repo stars
62. ▌
    Turn Notes Logs And Screenshots Into Structured Github Issue · agentskillexchange

    Convert messy bug notes, error logs, voice dictation, and screenshots into crisp GitHub issue reports with clear repro steps, impact, and evidence.
    28 repo stars
63. ▌
    Use An Escalating Scrape Strategy In Claude Code Before Reac · agentskillexchange

    Start with cheap static fetches, escalate to a browser only when needed, validate findings, and turn the result into a production-ready scraping approach.
    28 repo stars
64. ▌
    Verify Packages Are Reproducibly Rebuildable Before Trusting · agentskillexchange

    Query OSS Rebuild attestations and rebuild metadata so an agent can verify whether a published package artifact matches a reproducible upstream rebuild.
    28 repo stars
65. ▌
    Capture Local Screen And Audio Context So Agents Can Search · agentskillexchange

    Use Screenpipe when an agent needs private, local-first memory of what you saw or heard on your computer, including searchable screen text, app context, and transcripts, instead of relying on a chat-only memory layer.
    28 repo stars
66. ▌
    Collect Unix Like Incident Response Artifacts Into One Porta · agentskillexchange

    Capture volatile and persistent Unix-like system artifacts quickly before evidence disappears or responders start changing the host.
    28 repo stars
67. ▌
    Configure And Interpret Launchdarkly AI Config Online Evalua · agentskillexchange

    Attach judges to LaunchDarkly AI Config variations, create custom judges, set sampling rates, and interpret production quality signals from online evaluations.
    28 repo stars
68. ▌
    Enforce Package Boundaries Inside A Rails Monolith Before Co · agentskillexchange

    Check a Rails codebase for dependency and visibility violations so domain boundaries stay reviewable instead of dissolving over time.
    28 repo stars
69. ▌
    Enforce Source Controlled AI Checks In CI Before Merging Ris · agentskillexchange

    Lets an agent define repo-native AI review checks as markdown files and run them as repeatable pull request status checks in CI.
    28 repo stars
70. ▌
    Export Obsidian Vaults Into Clean Markdown Trees For Publish · agentskillexchange

    Convert Obsidian vault content, wikilinks, and attachments into portable Markdown trees before publishing, indexing, or migrating notes.
    28 repo stars
71. ▌
    Mirror Github Issues Pull Requests Commits And Releases Into · agentskillexchange

    Use dogsheep/github-to-sqlite when an agent needs a local, queryable snapshot of GitHub activity instead of bouncing through the web UI or ad hoc API calls. The agent authenticates once, pulls the exact GitHub objects it needs, and leaves behind a SQLite database that can be inspected, joined, diffed, or handed to downstream tools.
    28 repo stars
72. ▌
    Present Version Controlled Markdown Slide Decks As Terminal · agentskillexchange

    Turn markdown slide decks into terminal presentations for live demos, reviews, and workshops without leaving plain text or git.
    28 repo stars
73. ▌
    Run Autonomous Improve Verify Keep Or Revert Loops Across Co · agentskillexchange

    Turn Claude Code, OpenCode, or Codex into a metric-driven loop that makes one change at a time, verifies it mechanically, and keeps or reverts automatically.
    28 repo stars
74. ▌
    Scan MCP Servers For Security Findings Before Connecting The · agentskillexchange

    Run MCP Scanner against a remote or local MCP server before trusting it, so the agent gets a bounded security review of tools, prompts, resources, dependencies, and supply-chain risk.
    28 repo stars
75. ▌
    Statically Scan Agent Repos For Prompt Injection And Unsafe · agentskillexchange

    Audit agent code, prompts, and MCP configuration for prompt-injection surfaces, taint issues, and unsafe tool exposure before shipping.
    28 repo stars
76. ▌
    Summarize Urls Files Podcasts And Youtube Sources Into Agent · agentskillexchange

    Turn long pages, PDFs, podcasts, videos, and local files into compact working briefs before downstream research, drafting, or execution steps.
    28 repo stars
77. ▌
    Turn A Plain Language Brief Into A Multi Step Video Producti · agentskillexchange

    Use OpenMontage when an agent should take a brief or reference video and run the research, scripting, asset generation, editing, subtitle, and render pipeline as one production workflow instead of treating each media tool as a separate manual step.
    28 repo stars
78. ▌
    Turn Notion Specs Into Implementation Plans And Tasks With N · agentskillexchange

    Read a Notion spec, extract requirements and ambiguities, then create a linked implementation plan, task breakdown, and progress-tracking structure.
    28 repo stars
79. ▌
    Verify A Freshly Provisioned Server Or Container Matches Exp · agentskillexchange

    Uses Goss to express the expected state of a machine or container, then validates that reality still matches the contract. Reach for it after provisioning, image builds, or config changes when an agent needs a fast pass or fail answer about service health and system drift.
    28 repo stars
80. ▌
    Audit Python Environments And Requirements Files For Known V · agentskillexchange

    Check Python environments and requirements files for published vulnerabilities before shipping, upgrading, or approving dependency changes.
    28 repo stars
81. ▌
    Build And Debug Custom Wordpress REST API Endpoints With Sch · agentskillexchange

    Uses the WordPress wp-rest-api skill to help an agent design, register, validate, and troubleshoot custom REST routes without skipping schema, auth, or permission_callback details. This is for agent-led endpoint work in plugins, themes, or core-adjacent codebases, not for browsing the WordPress REST API as a product catalog.
    28 repo stars
82. ▌
    Capture Linux Runtime Security Events And Suspicious Behavio · agentskillexchange

    Watch live Linux and container activity through eBPF so you can triage suspicious runtime behavior before it disappears into guesswork.
    28 repo stars
83. ▌
    Draft Commit Messages Pr Descriptions And Changelog Updates · agentskillexchange

    Analyze staged changes, scan for sensitive content, draft Conventional Commit messages, prepare PR text, and update changelog entries in a guarded commit-and-release communication workflow.
    28 repo stars
84. ▌
    Install And Sync Reproducible Agent Dependencies Prompts And · agentskillexchange

    Use one manifest to reproduce agent setup across repositories so skills, prompts, plugins, and config stop drifting from machine to machine.
    28 repo stars
85. ▌
    Normalize International Phone Numbers Into E 164 Before Crm · agentskillexchange

    Use libphonenumber-js when an agent needs to clean messy phone-number input, validate it against country rules, and return a stable E.164 value before storing contacts or triggering downstream messaging. The skill is about normalization and validation, not telephony delivery, call routing, or campaign orchestration.
    28 repo stars
86. ▌
    Rewrite Fragile Shell Scripts Toward Safer Quoting And Stric · agentskillexchange

    Inspect or auto-fix shell scripts to reduce quoting bugs and brittle Bash patterns before they break in CI or production.
    28 repo stars
87. ▌
    Run React Native Implementation And Troubleshooting Workflow · agentskillexchange

    Give coding agents React Native-specific build, upgrade, GitHub Actions, and troubleshooting guidance instead of treating mobile work like generic web development.
    28 repo stars
88. ▌
    Search Large Codebases Semantically From MCP Compatible Codi · agentskillexchange

    Use Claude Context when a coding agent needs targeted semantic retrieval from a very large repository instead of repeatedly loading folders or files into prompt context. It indexes code into a vector database and exposes code-search retrieval through MCP for Claude Code and other compatible agent clients.
    28 repo stars
89. ▌
    Spin Up Isolated Git Worktrees For Parallel Claude Code And · agentskillexchange

    Create, switch, and clean per-branch worktrees so multiple coding agents can work the same repo in parallel without stomping each other.
    28 repo stars
90. ▌
    Benchmark Deep Research Agents Across Factual Quality And Pr · agentskillexchange

    Score deep research agents on benchmark tasks using factual verification, report-quality scoring, and process evaluation before model or workflow changes ship.
    28 repo stars
91. ▌
    Check Kubernetes Hosts Against Cis Guidance With Kube Bench · agentskillexchange

    Run a benchmark-driven posture check on Kubernetes nodes and control planes before an audit, upgrade, or hardening sprint starts.
    28 repo stars
92. ▌
    Drive Web And App Uis With Vision Grounded Steps When Select · agentskillexchange

    Use Midscene.js when an agent needs screenshot-grounded UI actions and assertions across web, mobile, or desktop surfaces where DOM selectors are fragile, unavailable, or not the right abstraction.
    28 repo stars
93. ▌
    Find Deprecated Kubernetes Apis In Manifests And Live Resour · agentskillexchange

    Scan Helm charts, YAML, or live clusters for Kubernetes API versions scheduled for removal before an upgrade window.
    28 repo stars
94. ▌
    Prepare Meeting Agendas And Pre Reads From Notion Context Wi · agentskillexchange

    Pull relevant Notion context, tailor an agenda to attendees and decisions, and assemble a structured pre-read for an upcoming meeting.
    28 repo stars
95. ▌
    Red Team Agent Workflows For Jailbreaks Prompt Injection And · agentskillexchange

    Run local adversarial attack passes against agents, RAG pipelines, and chatbots to surface concrete failure classes before production rollout.
    28 repo stars
96. ▌
    Resolve Syntax Aware Git Merge Conflicts Before Escalating T · agentskillexchange

    Use Mergiraf to let an agent attempt tree-aware conflict resolution during merge, rebase, revert, or cherry-pick before falling back to manual edits.
    28 repo stars
97. ▌
    Review Pull Requests With Structured Summaries Checks And Fo · agentskillexchange

    Use PR-Agent when an agent should run an automated pull request review pass with summaries, comments, improvement prompts, or ask-mode follow-ups before human merge review.
    28 repo stars
98. ▌
    Review REST API Designs Before Implementation For Versioning · agentskillexchange

    Review an API design, endpoint set, or OpenAPI spec before implementation and return prioritized findings on design quality, security, resilience, and missing contract decisions.
    28 repo stars
99. ▌
    Start Governed Claude Code Sessions With Short Lived Service · agentskillexchange

    Inject short-lived, scoped service credentials into Claude Code sessions so agents can reach approved systems without exposing raw secrets.
    28 repo stars
100. ▌
     Apply Repeatable Javascript And Typescript Codemods Across L · agentskillexchange

     Use jscodeshift when an agent needs AST-based JavaScript or TypeScript codemods for bulk migrations, API rewrites, and large refactors with reviewable diffs.
     28 repo stars